© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50908
    Prev
    Next
    INDEX
    Explanations

    why questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iel
    -0.08
    ×Ļר×ķ
    -0.07
    TabIndex
    -0.07
    éľĵ
    -0.07
    riel
    -0.07
    天å®ī
    -0.06
    åıªæľīèĩªå·±
    -0.06
    å¤ļå°ij人
    -0.06
    æľīæīį
    -0.06
    åIJijæĹ¥
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Īåģļ
    0.09
    ool
    0.07
    å¥ı
    0.07
    è¿Ļæł·çļĦ
    0.07
    åĪ«çľĭ
    0.07
    ulus
    0.07
    Bow
    0.07
    adaan
    0.07
    AspNet
    0.07
    icans
    0.07
    Activations Density 0.030%

    No Known Activations